From c62b4f35aa2c59d7db0fd177affeed14b1ba4bcb Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Thu, 08 Sep 2016 07:04:39 +0000
Subject: [PATCH] adding coco models
---
src/data.c | 40 +++++++++++++++++++++-------------------
1 files changed, 21 insertions(+), 19 deletions(-)
diff --git a/src/data.c b/src/data.c
index 9aa08af..02dbac4 100644
--- a/src/data.c
+++ b/src/data.c
@@ -100,7 +100,7 @@
return X;
}
-matrix load_image_augment_paths(char **paths, int n, int min, int max, int size, float angle, float exposure, float saturation)
+matrix load_image_augment_paths(char **paths, int n, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure)
{
int i;
matrix X;
@@ -110,13 +110,10 @@
for(i = 0; i < n; ++i){
image im = load_image_color(paths[i], 0, 0);
- image crop = random_augment_image(im, angle, min, max, size);
+ image crop = random_augment_image(im, angle, aspect, min, max, size);
int flip = rand_r(&data_seed)%2;
if (flip) flip_image(crop);
- float exp = rand_uniform(1./exposure, exposure);
- float sat = rand_uniform(1./saturation, saturation);
- exposure_image(crop, exp);
- exposure_image(crop, sat);
+ random_distort_image(crop, hue, saturation, exposure);
/*
show_image(im, "orig");
@@ -241,6 +238,7 @@
labelpath = find_replace(labelpath, "JPEGImages", "labels");
labelpath = find_replace(labelpath, ".jpg", ".txt");
+ labelpath = find_replace(labelpath, ".png", ".txt");
labelpath = find_replace(labelpath, ".JPG", ".txt");
labelpath = find_replace(labelpath, ".JPEG", ".txt");
int count = 0;
@@ -287,6 +285,7 @@
labelpath = find_replace(labelpath, "JPEGImages", "labels");
labelpath = find_replace(labelpath, ".jpg", ".txt");
+ labelpath = find_replace(labelpath, ".png", ".txt");
labelpath = find_replace(labelpath, ".JPG", ".txt");
labelpath = find_replace(labelpath, ".JPEG", ".txt");
int count = 0;
@@ -443,7 +442,7 @@
}
}
-data load_data_region(int n, char **paths, int m, int w, int h, int size, int classes, float jitter)
+data load_data_region(int n, char **paths, int m, int w, int h, int size, int classes, float jitter, float hue, float saturation, float exposure)
{
char **random_paths = get_random_paths(paths, n, m);
int i;
@@ -485,6 +484,7 @@
image sized = resize_image(cropped, w, h);
if(flip) flip_image(sized);
+ random_distort_image(sized, hue, saturation, exposure);
d.X.vals[i] = sized.data;
fill_truth_region(random_paths[i], d.y.vals[i], classes, size, flip, dx, dy, 1./sx, 1./sy);
@@ -611,7 +611,7 @@
return d;
}
-data load_data_detection(int n, char **paths, int m, int w, int h, int boxes, int classes, float jitter)
+data load_data_detection(int n, char **paths, int m, int w, int h, int boxes, int classes, float jitter, float hue, float saturation, float exposure)
{
char **random_paths = get_random_paths(paths, n, m);
int i;
@@ -651,6 +651,7 @@
image sized = resize_image(cropped, w, h);
if(flip) flip_image(sized);
+ random_distort_image(sized, hue, saturation, exposure);
d.X.vals[i] = sized.data;
fill_truth_detection(random_paths[i], boxes, d.y.vals[i], classes, flip, dx, dy, 1./sx, 1./sy);
@@ -675,21 +676,22 @@
load_args a = *(struct load_args*)ptr;
if(a.exposure == 0) a.exposure = 1;
if(a.saturation == 0) a.saturation = 1;
+ if(a.aspect == 0) a.aspect = 1;
if (a.type == OLD_CLASSIFICATION_DATA){
*a.d = load_data(a.paths, a.n, a.m, a.labels, a.classes, a.w, a.h);
} else if (a.type == CLASSIFICATION_DATA){
- *a.d = load_data_augment(a.paths, a.n, a.m, a.labels, a.classes, a.min, a.max, a.size, a.angle, a.exposure, a.saturation);
+ *a.d = load_data_augment(a.paths, a.n, a.m, a.labels, a.classes, a.min, a.max, a.size, a.angle, a.aspect, a.hue, a.saturation, a.exposure);
} else if (a.type == SUPER_DATA){
*a.d = load_data_super(a.paths, a.n, a.m, a.w, a.h, a.scale);
} else if (a.type == STUDY_DATA){
- *a.d = load_data_study(a.paths, a.n, a.m, a.labels, a.classes, a.min, a.max, a.size, a.angle, a.exposure, a.saturation);
+ *a.d = load_data_study(a.paths, a.n, a.m, a.labels, a.classes, a.min, a.max, a.size, a.angle, a.aspect, a.hue, a.saturation, a.exposure);
} else if (a.type == WRITING_DATA){
*a.d = load_data_writing(a.paths, a.n, a.m, a.w, a.h, a.out_w, a.out_h);
} else if (a.type == REGION_DATA){
- *a.d = load_data_region(a.n, a.paths, a.m, a.w, a.h, a.num_boxes, a.classes, a.jitter);
+ *a.d = load_data_region(a.n, a.paths, a.m, a.w, a.h, a.num_boxes, a.classes, a.jitter, a.hue, a.saturation, a.exposure);
} else if (a.type == DETECTION_DATA){
- *a.d = load_data_detection(a.n, a.paths, a.m, a.w, a.h, a.num_boxes, a.classes, a.jitter);
+ *a.d = load_data_detection(a.n, a.paths, a.m, a.w, a.h, a.num_boxes, a.classes, a.jitter, a.hue, a.saturation, a.exposure);
} else if (a.type == SWAG_DATA){
*a.d = load_data_swag(a.paths, a.n, a.classes, a.jitter);
} else if (a.type == COMPARE_DATA){
@@ -698,7 +700,7 @@
*(a.im) = load_image_color(a.path, 0, 0);
*(a.resized) = resize_image(*(a.im), a.w, a.h);
} else if (a.type == TAG_DATA){
- *a.d = load_data_tag(a.paths, a.n, a.m, a.classes, a.min, a.max, a.size, a.angle, a.exposure, a.saturation);
+ *a.d = load_data_tag(a.paths, a.n, a.m, a.classes, a.min, a.max, a.size, a.angle, a.aspect, a.hue, a.saturation, a.exposure);
//*a.d = load_data(a.paths, a.n, a.m, a.labels, a.classes, a.w, a.h);
}
free(ptr);
@@ -740,13 +742,13 @@
return d;
}
-data load_data_study(char **paths, int n, int m, char **labels, int k, int min, int max, int size, float angle, float exposure, float saturation)
+data load_data_study(char **paths, int n, int m, char **labels, int k, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure)
{
data d = {0};
d.indexes = calloc(n, sizeof(int));
if(m) paths = get_random_paths_indexes(paths, n, m, d.indexes);
d.shallow = 0;
- d.X = load_image_augment_paths(paths, n, min, max, size, angle, exposure, saturation);
+ d.X = load_image_augment_paths(paths, n, min, max, size, angle, aspect, hue, saturation, exposure);
d.y = load_labels_paths(paths, n, labels, k);
if(m) free(paths);
return d;
@@ -782,25 +784,25 @@
return d;
}
-data load_data_augment(char **paths, int n, int m, char **labels, int k, int min, int max, int size, float angle, float exposure, float saturation)
+data load_data_augment(char **paths, int n, int m, char **labels, int k, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure)
{
if(m) paths = get_random_paths(paths, n, m);
data d = {0};
d.shallow = 0;
- d.X = load_image_augment_paths(paths, n, min, max, size, angle, exposure, saturation);
+ d.X = load_image_augment_paths(paths, n, min, max, size, angle, aspect, hue, saturation, exposure);
d.y = load_labels_paths(paths, n, labels, k);
if(m) free(paths);
return d;
}
-data load_data_tag(char **paths, int n, int m, int k, int min, int max, int size, float angle, float exposure, float saturation)
+data load_data_tag(char **paths, int n, int m, int k, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure)
{
if(m) paths = get_random_paths(paths, n, m);
data d = {0};
d.w = size;
d.h = size;
d.shallow = 0;
- d.X = load_image_augment_paths(paths, n, min, max, size, angle, exposure, saturation);
+ d.X = load_image_augment_paths(paths, n, min, max, size, angle, aspect, hue, saturation, exposure);
d.y = load_tags_paths(paths, n, k);
if(m) free(paths);
return d;
--
Gitblit v1.10.0